view article Article The Ambiguous State Trap: Why I Disabled Claude's Auto-Memory dacorvo • 16 days ago
view article Article TorchNeuron: running HF models on AWS Trainium is easier than ever +5 regisss, pagezyhf, michaelbenayoun, Jingya, tengomucho, dacorvo, jeffboudier • 19 days ago • 32
view article Article 150k Tokens Deep: Why Context Recall Beats Compaction by up to 8x dacorvo • Oct 1 • 3
view article Article Follow the White Rabbit: Using Embeddings So You Never Get Lost in Translation dacorvo • Feb 23 • 8
view article Article How to deploy and fine-tune DeepSeek models on AWS +1 pagezyhf, jeffboudier, dacorvo • Jan 30, 2025 • 56
view article Article Memory-efficient Diffusion Transformers with Quanto and Diffusers sayakpaul, dacorvo • Jul 30, 2024 • 68
view article Article Quanto: a PyTorch quantization backend for Optimum +1 dacorvo, ybelkada, marcsun13 • Mar 18, 2024 • 45
view article Article Hugging Face Text Generation Inference available for AWS Inferentia2 philschmid, dacorvo • Feb 1, 2024 • 5
view article Article Make your llama generation time fly with AWS Inferentia2 dacorvo • Nov 7, 2023 • 1
view article Article Make your llama generation time fly with AWS Inferentia2 dacorvo • Nov 7, 2023 • 1